LeapLabTHU/DAT-Detection

Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention

22
/ 100
Experimental

This project offers advanced tools for precisely identifying and segmenting objects within images. It takes raw image data and outputs detailed bounding box coordinates for detected objects, along with pixel-level masks for each instance. This is ideal for computer vision researchers and engineers who need to develop and benchmark high-performance object detection and instance segmentation models.

No commits in the last 6 months.

Use this if you are building state-of-the-art computer vision systems that require highly accurate object localization and segmentation, and you need to leverage the latest advancements in Vision Transformers.

Not ideal if you are a beginner looking for a simple, out-of-the-box solution without deep understanding of model training or evaluation, or if your primary need is general image classification.

computer-vision object-detection image-segmentation machine-learning-research model-benchmarking
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

20

Forks

2

Language

Python

License

Last pushed

Apr 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/LeapLabTHU/DAT-Detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.